A Knowledge Based Cloud-Expert System for Disease Diagnosis

Abstract

Expert systems are among the most widely used types of knowledge- based systems. Because these systems mimic how human professionals make decisions, they are helpful for complex analysis, calculations, and forecasts. Knowledge-based systems can aid expert decision-making, especially when human experts are unavailable. Make efficient documentation simply available to users. Generate new understanding by looking over and examining previously stored information. The research's goal is to develop a knowledge-based cloud expert system for heart disease diagnosis. Internet of Things (IoT) devices create a huge quantity of big data in the healthcare setting. Cloud computing (CC) technology is utilized to manage massive data volumes and offers user-friendliness. In this case, CC technology is being utilized by healthcare applications to monitor and diagnose heart diseases. In this study, a novel adaptive Squirrel Search fine-tuned Fuzzy Decision Trees (ASS-FDT) is proposed to classify and diagnose heart disease and its severity. The expert system is comprised of an extensive knowledge base that is derived from reliable databases and includes clinical recommendations, symptoms, treatment regimens, and medical information. Gathering distinctive patient data is retrieved through the use of wearable IoT devices that rely on sensors. The results demonstrated the proposed method is achieving superior performance in accuracy (98.90%), recall (98.90%), and specificity (98.98%) in heart disease diagnosis compared to other existing algorithms. The cloud expert system is a useful tool for healthcare professionals as it makes accessibility and integration into current infrastructures accessible.